@bolagsapi/mcp-server
MCP server for Swedish company data. Enables AI agents to lookup companies, analyze financials, assess health, screen compliance, and get industry stats.
README
@bolagsapi/mcp-server
Official MCP (Model Context Protocol) server for BolagsAPI - Swedish company data for AI agents.
Enables Claude, ChatGPT, and other AI agents to access comprehensive Swedish company information including:
- Company lookup and search
- Financial analysis from annual reports
- Financial health and stability analysis
- Compliance screening (sanctions, PEP)
- Industry statistics and benchmarks
Installation
npm install -g @bolagsapi/mcp-server
Or use npx:
npx @bolagsapi/mcp-server
Requirements
- Node.js 18+
- BolagsAPI key (get one at bolagsapi.se/dashboard)
Quick Start
Claude Desktop
Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"bolagsapi": {
"command": "npx",
"args": ["-y", "@bolagsapi/mcp-server"],
"env": {
"BOLAGSAPI_KEY": "sk_live_your_api_key_here"
}
}
}
}
Cursor IDE
Add to .cursor/mcp.json in your project:
{
"mcpServers": {
"bolagsapi": {
"command": "npx",
"args": ["-y", "@bolagsapi/mcp-server"],
"env": {
"BOLAGSAPI_KEY": "sk_live_your_api_key_here"
}
}
}
}
VS Code with Continue
Add to your Continue configuration:
{
"experimental": {
"modelContextProtocolServers": [
{
"transport": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@bolagsapi/mcp-server"],
"env": {
"BOLAGSAPI_KEY": "sk_live_your_api_key_here"
}
}
}
]
}
}
Available Tools
Company Intelligence
| Tool | Description |
|---|---|
lookup_company |
Get comprehensive company info by organization number |
search_companies |
Search companies by name with filters |
get_company_timeline |
Historical events and milestones |
get_similar_companies |
Find peer companies by industry |
Financial & Health
| Tool | Description |
|---|---|
analyze_company_financials |
Financial data + AI analysis from annual reports |
assess_financial_health |
Health score, stability grade, financial flags |
get_annual_reports |
List available annual reports |
Compliance & Reference
| Tool | Description |
|---|---|
get_compliance_data |
Sanctions and PEP screening |
get_industry_stats |
Industry benchmarks by SNI code |
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
BOLAGSAPI_KEY |
Yes | - | Your BolagsAPI key |
BOLAGSAPI_URL |
No | https://api.bolagsapi.se/v1 |
API base URL |
HTTP Transport (Remote)
For remote deployments, use the HTTP transport:
# Start HTTP server
npm run start:http
# Or with Docker
docker build -t bolagsapi-mcp .
docker run -p 3001:3001 -e BOLAGSAPI_KEY=sk_live_xxx bolagsapi-mcp
Environment variables for HTTP mode:
PORT: HTTP port (default: 3001)HOST: Bind address (default: 127.0.0.1)
HTTP Authentication
The HTTP transport requires Bearer token authentication:
curl -X POST http://localhost:3001/mcp \
-H "Authorization: Bearer sk_live_your_api_key" \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","method":"tools/list","id":1}'
Example Usage
Once configured, you can ask Claude:
"Look up information about Spotify (org nr 556703-7485)"
"Search for AI companies in Stockholm"
"Analyze the financials for IKEA"
"Check if company 5566778899 has any sanctions hits"
"What's the financial health of org 556677-8899?"
Development
# Clone the repo
git clone https://github.com/HugoAndFriends/BolagsAPI-mcp-server.git
cd BolagsAPI-mcp-server
# Install dependencies
pnpm install
# Run in development mode
BOLAGSAPI_KEY=sk_live_xxx pnpm dev
# Build
pnpm build
Security
- API keys are validated against the BolagsAPI backend
- Rate limiting: 100 requests/minute per IP (HTTP mode)
- DNS rebinding protection for localhost bindings
- CORS enabled for browser clients
Support
- Documentation: bolagsapi.se/docs
- Issues: github.com/HugoAndFriends/BolagsAPI-mcp-server/issues
- Email: dev@bolagsapi.se
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。